Notification Channel Optimizer — Multi-Armed Bandit Live

Selection Strategy

Exploration rate ε 10%

Messages / second 2.0

Live Stats

Messages sent

Cumulative regret

0.00

Best estimated channel

—

Overall open rate

0.0%

Channels (true rate hidden from AI)

How it works

Each government alert must go out on exactly one channel, and the AI does not know in advance which channel citizens actually open. This is the classic multi-armed bandit problem: every message is a trial that both earns a reward (opened / not opened) and reveals information about that channel's true, hidden open-rate p_i.

Epsilon-greedy:
  with probability ε        → pick a uniformly random channel (explore)
  with probability 1-ε      → pick argmax_i p̂_i (exploit best-so-far)

UCB1 (Upper Confidence Bound):
  score_i(t) = p̂_i + sqrt( 2·ln(t) / n_i )
  pick argmax_i score_i(t)   (unpulled arms score +∞ and go first)

Regret after T messages:
  R(T) = T·p* − Σ p_chosen(t)     where p* = max_i p_i

p̂_i is the running sample mean of opens/sends for channel i — the AI's current belief, shown as each tower's height.
Epsilon-greedy explores at a constant rate forever, so it keeps sampling weak channels occasionally even late in the run.
UCB1 shrinks its exploration bonus as sqrt(ln t / n_i), so it explores heavily at first and converges onto the best channel without a fixed ε.
Cumulative regret is the gap between what an oracle (always picking the true-best channel) would have earned and what the algorithm actually earned — a flattening regret curve means the algorithm has converged.

Real-world relevance: this exact reward-per-arm setup drives production notification routing at scale — deciding, per user segment, whether SMS, email, push or postal mail gets the next message, and adapting as citizens' real response habits emerge.

Opened Not opened Estimate p̂ (bar height)

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.